© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34345
    Prev
    Next
    INDEX
    Explanations

    http://

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įå¿ĺ
    -0.10
    鸾
    -0.09
    æĿijæĿijæ°ij
    -0.09
    çĦ¶æĺ¯
    -0.09
    rio
    -0.09
    纪å½ķ
    -0.09
    çĶļ
    -0.09
    æ·±æĥħ
    -0.09
    elps
    -0.09
    åĩĽ
    -0.09
    POSITIVE LOGITS
    www
    0.12
    ones
    0.10
    ร
    0.09
    çĶŁæĢķ
    0.09
    ../
    0.09
     ÑģпеÑĨиалÑĮно
    0.09
    orary
    0.09
     www
    0.09
     Wagner
    0.09
    гла
    0.08
    Activations Density 0.215%

    No Known Activations